DEV Community: Muhammad Falih Afiq

Touch Grass

Muhammad Falih Afiq — Wed, 14 Oct 2026 14:41:13 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass

What I Built

🌿 Touch Grass AI — Your Offline Outdoor Companion

Touch Grass AI is an AI-powered outdoor companion designed to help people spend less time staring at screens and more time exploring the real world.

The idea is simple: tell the app how you feel, how much time you have, and what kind of outdoor experience you want. It suggests simple activities such as taking a nature walk, exploring a nearby park, observing birds, starting a small garden, or taking a break from technology.

Instead of encouraging people to keep scrolling, Touch Grass AI turns AI suggestions into real-world actions.

It's designed for students, remote workers, and anyone who needs a little encouragement to step outside and reconnect with nature.

Demo

A live demo or video walkthrough will be added here once the application is ready.

Code

The source code will be available on GitHub.

GitHub Repository: [Add your repository link here]

How I Built It

Touch Grass AI is designed around open-weight AI and local inference.

The planned tech stack includes:

Python for the application logic.
Ollama to run language models locally.
Qwen, an open-weight language model, to generate personalized outdoor activity suggestions.
Streamlit to build a simple, user-friendly interface.

Users provide basic information such as their available time, preferred activities, and energy level. The local AI model uses this information to suggest practical activities that encourage them to go outside.

The application can be designed to work offline after the model has been downloaded, making it useful even when an internet connection is unavailable.

The focus is on keeping the interaction short: get a suggestion, put the phone away, and go outside.

Why Does Open Innovation Matter?

Open innovation makes Touch Grass AI more flexible, private, and accessible.

With local inference, personal preferences and conversations can stay on the user's device instead of being sent to an external AI provider for every request.

Open-weight models also give developers the freedom to experiment with different models, customize prompts, and adapt the assistant to different users and environments.

Unlike an application that depends entirely on a paid, closed AI API, this approach can avoid per-request API fees and potentially work without an internet connection.

Most importantly, the technology supports the project's purpose. AI should not always demand more of our attention. Sometimes, its best job is to give us a reason to put our devices down and experience the world around us.

My Agent Session

My DevRelay agent session will be added here if available.

Prize Categories

To be determined based on the eligible partner categories and the tools used in the final implementation.

Friends

Muhammad Falih Afiq — Wed, 14 Oct 2026 14:39:27 +0000

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend

What I Built

I built StudyBuddy AI, a personal AI study assistant designed to help a friend learn more effectively.

StudyBuddy AI helps students understand difficult topics, summarize study materials, generate practice questions, and learn at their own pace. Instead of being a generic chatbot, the goal is to create a helpful learning companion that focuses on one person's needs.

I wanted to build something meaningful for a friend because learning can sometimes feel overwhelming, especially when there is no one available to explain a difficult concept.

Demo

A live demo or video walkthrough will be added here once the application is ready.

Code

The source code will be available on GitHub.

GitHub Repository: [Add your repository link here]

How I Built It

StudyBuddy AI is designed around open-source AI technology.

The planned tech stack includes:

Python for the application logic.
Ollama for running language models locally.
An open-weight language model, such as Qwen, for generating explanations and practice questions.
Streamlit for a simple, interactive user interface.

The application sends questions to the locally running model and displays the generated answers in a user-friendly interface. The model and prompts can be changed to experiment with different learning styles and response quality.

The goal is to make the application useful without depending entirely on a paid, closed-source AI API.

Why Does Open Innovation Matter?

Open innovation matters because AI tools should be adaptable to the people who use them.

With open-weight models and local inference, StudyBuddy AI can potentially run without sending every question or study note to an external AI provider. Once the required model is downloaded, local functionality can work without an internet connection.

Using open models also gives developers more control. I can experiment with different models, customize prompts, inspect the application code, and improve the learning experience based on feedback.

For a personal learning assistant, privacy, flexibility, and accessibility are important. Open-source tools make it easier to experiment and build something useful without making a closed API the foundation of the entire project.

My Agent Session

My DevRelay agent session will be added here if available.

Prize Categories

To be determined based on the eligible partner categories and the tools used in the final implementation.

CNZR Framework

Muhammad Falih Afiq — Wed, 14 Oct 2026 13:33:11 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built

I built CNZR Framework, a lightweight, modular open-source framework designed to help developers and indie hackers rapidly build, orchestrate, and deploy AI-powered workflows and applications without boilerplate bloat.

Who would pay for it & what problem does it solve?
Solo developers, small agencies, and startups waste days wiring up repetitive architecture, model routing, and tool execution every time they start a new project. CNZR Framework solves this by providing a clean, structured foundation out of the box. While the core framework is open-source, teams and freelance developers would happily pay for managed cloud templates, enterprise plugins, or pro starter kits built on top of CNZR because it cuts MVP development time from weeks to hours.

Demo

GitHub Profile & Project: github.com/Cenzer0
Live Demo / Documentation: [Link to your demo or docs here]

Code

Cenzer0 / cnzr

A modern, minimalist yet powerful Node.js web framework built with TypeScript. Designed to be fast, developer-friendly, and feature-rich while maintaining simplicity. Competitive with Express.js, Fastify, and Hono.

Cenzero Framework (cnzr)

Now at v2.5 with faster route matching and an Astro-inspired animated CLI installer.

A modern, minimalist yet powerful Node.js web framework built with TypeScript. Designed to be fast, developer-friendly, and feature-rich while maintaining simplicity. Competitive with Express.js, Fastify, and Hono.

🚀 Features

Core Framework

🎯 Advanced Routing - File-based routing with dynamic parameters [id] and catch-all [...slug]
🔧 Dual Middleware - Support for both legacy (req, res, next) and modern (ctx, next) patterns
🏗️ Plugin System - Extensible architecture with hooks (onRequest, onResponse, onError, etc.)
📦 Context Object - Rich context with request/response wrappers, state management, utilities
🍪 Session & Cookies - Built-in session management with secure defaults
🔒 Security - CORS, security headers, request validation
� Enhanced Logging - Multi-level, colored output with request timing
❌ Error Handling - Comprehensive error management with custom handlers

Developer Experience

🛠️ Enhanced CLI - Project scaffolding, development server, build…

View on GitHub

(Catatan: Ganti Cenzer0/cnzr di atas dengan nama spesifik repositori kamu jika berbeda)

How I Built It

I architected and built CNZR Framework using Claude as my primary AI pair-programmer and coding agent, designing the framework around the open-source AI ecosystem:

AI-Assisted Development with Claude: I used Claude to iterate on the core architecture, design clean abstractions, debug edge cases, and generate modular components rapidly.
Open-Source AI Integration: CNZR Framework is built to be model-agnostic and open-source friendly—allowing developers to seamlessly plug in open-weight models (such as Llama 3, Qwen, or DeepSeek) via local inference engines like Ollama, vLLM, or OpenAI-compatible endpoints, alongside standard APIs.
Core Architecture: Built with a focus on developer experience (DX), modularity, and low overhead so it can run efficiently even on local hardware or affordable VPS instances.

Why Does Open Innovation Matter?

When building a side hustle or bootstrapping a developer tool, vendor lock-in and unpredictable API token bills can kill a project before it gets traction. Open innovation matters for CNZR Framework because:

Zero-Cost Local Prototyping: Developers can build and test their entire workflow using local open-weight models without spending a dime on closed APIs.
Full Transparency & Customizability: Unlike rigid closed platforms, an open-source framework lets developers inspect the internals, customize the execution pipeline, and self-host with 100% data privacy.
Community-Driven Growth: Open-sourcing the core under github.com/Cenzer0 allows other builders to contribute plugins, adapters, and improvements that benefit everyone.

My Agent Session

I collaborated extensively with Claude throughout the development of CNZR Framework—from scaffolding the initial repository structure to refining the core logic and documentation.

My First User

I tested the initial release of CNZR Framework on my own workflow and shared the repository with fellow developers for early feedback. Early testers highlighted how clean the setup is compared to heavier frameworks, making it much easier to spin up new side projects quickly.

Prize Categories

Open-Source AI / Side Hustle (Tambahkan kategori sponsor spesifik dari halaman challenge jika ada yang cocok, atau hapus bagian ini)